.png){kind=icon}
.png){kind=icon}
Return
Spatial and Temporal Modeling Approach to Urban Sprawl: A Comparative Analysis of Artificial Intelligence and AHP-Based Approaches
.png){kind=icon}
PRE
AI
A
S
T
DOI：10.26833/ijeg.1727806.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Urban sprawl is a significant phenomenon that emerges from the growth process of settlement areas, which has evolved over time. The historical background and geographical characteristics of a city directly influence its sprawl process. Additionally, the changing sectoral structure of the city, population growth, technological advancements, and economic fluctuations can indirectly affect the direction, speed, and extent of urban sprawl, potentially leading to adverse outcomes. Therefore, it is essential to monitor this process and implement spatial and temporal modeling to keep urban sprawl under control. This study simulates urban sprawl in Konya, a city with valuable agricultural lands, for the year 2040 using two scenarios based on expert knowledge and artificial intelligence. The first scenario combines the Analytic Hierarchy Process (AHP) for weighting sprawl criteria with Cellular Automata (CA), while the second scenario employs Artificial Neural Networks (ANN) with CA to predict future land use changes. Both models used six spatial datasets (DEM, slope, aspect, distances to streams, roads, and protected areas) and CORINE land use maps (2000, 2018), with the 2023 map obtained from Konya GIS data. Model performance was evaluated by comparing simulated and actual 2023 maps using accuracy, Kappa, precision, recall, and F1-score; AHP-CA achieved 96.13 % accuracy and 0.94 Kappa, whereas ANN-CA reached 92.13 % and 0.89, indicating both models reliably capture urban dynamics, with AHP-CA performing better. Both scenarios predict inevitable urban expansion, but the expert-based AHP-CA scenario better preserves agricultural lands and natural vegetation. Based on these results, the study discusses the directions and factors influencing urban change and provides spatial planning recommendations for urban
Keywords:
Urban Sprawl
Cellular Automata
AHP
Artificial Neural Networks
GIS
Journal
I
IF:
2.5
Papers:
160
Citations:
348
Organization
Cited Papers